Advances In Multimodal Tracking Of Driver Distraction

This chapter discusses research efforts focused on tracking driver distraction using multimodal features. A car equipped with various sensors is used to collect a database with real driving conditions. During the recording, the drivers were asked to perform common secondary tasks such as operating a cell phone, talking to another passenger, and changing the radio stations. We analyzed the differences observed across multimodal features when the driver was engaged in these secondary tasks. The study considers features extracted from the controller area network bus (CAN-bus), a frontal camera facing the driver, and a microphone. These features are used to predict the distraction level of the drivers. The output of the proposed regression model has high correlation with human subjective evaluations (rho = 0.728), which validates our approach.